LST-AI: A deep learning ensemble for accurate MS lesion segmentation

•Free and open-source lesion-segmentation tool (LST-AI), allowing widespread use and community contributions.•Tested on multiple external datasets and consistently outperforms existing models.•Ensemble of 3D U-Nets and composite loss functions to optimize performance.•Enhanced detection rate, especi...

Full description

Saved in:
Bibliographic Details
Published inNeuroImage clinical Vol. 42; p. 103611
Main Authors Wiltgen, Tun, McGinnis, Julian, Schlaeger, Sarah, Kofler, Florian, Voon, CuiCi, Berthele, Achim, Bischl, Daria, Grundl, Lioba, Will, Nikolaus, Metz, Marie, Schinz, David, Sepp, Dominik, Prucker, Philipp, Schmitz-Koep, Benita, Zimmer, Claus, Menze, Bjoern, Rueckert, Daniel, Hemmer, Bernhard, Kirschke, Jan, Mühlau, Mark, Wiestler, Benedikt
Format Journal Article
LanguageEnglish
Published Netherlands Elsevier Inc 2024
Elsevier
Subjects
N/A
CNN
MRI
PV
CPU
GPU
SC
ASD
DSC
WM
PPV
ON
MS
AI
IQR
IT
CIS
LST
TE
TI
JC
FA
T1w
TR
Online AccessGet full text
ISSN2213-1582
2213-1582
DOI10.1016/j.nicl.2024.103611

Cover

Abstract •Free and open-source lesion-segmentation tool (LST-AI), allowing widespread use and community contributions.•Tested on multiple external datasets and consistently outperforms existing models.•Ensemble of 3D U-Nets and composite loss functions to optimize performance.•Enhanced detection rate, especially for small lesions 10–100 mm3.•Includes lesion location annotation per 2017 McDonald criteria. Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63—surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
AbstractList •Free and open-source lesion-segmentation tool (LST-AI), allowing widespread use and community contributions.•Tested on multiple external datasets and consistently outperforms existing models.•Ensemble of 3D U-Nets and composite loss functions to optimize performance.•Enhanced detection rate, especially for small lesions 10–100 mm3.•Includes lesion location annotation per 2017 McDonald criteria. Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63—surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm and 100 mm . Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets.LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models.Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63—surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.
Highlights•Free and open-source lesion-segmentation tool (LST-AI), allowing widespread use and community contributions. •Tested on multiple external datasets and consistently outperforms existing models. •Ensemble of 3D U-Nets and composite loss functions to optimize performance. •Enhanced detection rate, especially for small lesions 10–100 mm 3. •Includes lesion location annotation per 2017 McDonald criteria.
ArticleNumber 103611
Author Kofler, Florian
Mühlau, Mark
Metz, Marie
Schinz, David
Menze, Bjoern
Wiltgen, Tun
Berthele, Achim
Schmitz-Koep, Benita
Zimmer, Claus
Sepp, Dominik
Bischl, Daria
Kirschke, Jan
Schlaeger, Sarah
Wiestler, Benedikt
Voon, CuiCi
McGinnis, Julian
Prucker, Philipp
Rueckert, Daniel
Hemmer, Bernhard
Will, Nikolaus
Grundl, Lioba
Author_xml – sequence: 1
  givenname: Tun
  orcidid: 0000-0002-2682-3641
  surname: Wiltgen
  fullname: Wiltgen, Tun
  organization: Department of Neurology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 2
  givenname: Julian
  surname: McGinnis
  fullname: McGinnis, Julian
  organization: Department of Neurology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 3
  givenname: Sarah
  surname: Schlaeger
  fullname: Schlaeger, Sarah
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 4
  givenname: Florian
  surname: Kofler
  fullname: Kofler, Florian
  organization: Department of Computer Science, Institute for AI in Medicine, Technical University of Munich, Munich, Germany
– sequence: 5
  givenname: CuiCi
  surname: Voon
  fullname: Voon, CuiCi
  organization: Department of Neurology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 6
  givenname: Achim
  surname: Berthele
  fullname: Berthele, Achim
  organization: Department of Neurology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 7
  givenname: Daria
  surname: Bischl
  fullname: Bischl, Daria
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 8
  givenname: Lioba
  surname: Grundl
  fullname: Grundl, Lioba
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 9
  givenname: Nikolaus
  surname: Will
  fullname: Will, Nikolaus
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 10
  givenname: Marie
  surname: Metz
  fullname: Metz, Marie
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 11
  givenname: David
  surname: Schinz
  fullname: Schinz, David
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 12
  givenname: Dominik
  surname: Sepp
  fullname: Sepp, Dominik
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 13
  givenname: Philipp
  surname: Prucker
  fullname: Prucker, Philipp
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 14
  givenname: Benita
  surname: Schmitz-Koep
  fullname: Schmitz-Koep, Benita
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 15
  givenname: Claus
  surname: Zimmer
  fullname: Zimmer, Claus
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 16
  givenname: Bjoern
  surname: Menze
  fullname: Menze, Bjoern
  organization: Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
– sequence: 17
  givenname: Daniel
  surname: Rueckert
  fullname: Rueckert, Daniel
  organization: Department of Computer Science, Institute for AI in Medicine, Technical University of Munich, Munich, Germany
– sequence: 18
  givenname: Bernhard
  surname: Hemmer
  fullname: Hemmer, Bernhard
  organization: Department of Neurology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 19
  givenname: Jan
  surname: Kirschke
  fullname: Kirschke, Jan
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 20
  givenname: Mark
  orcidid: 0000-0002-9545-2709
  surname: Mühlau
  fullname: Mühlau, Mark
  email: mark.muehlau@tum.de
  organization: Department of Neurology, School of Medicine, Technical University of Munich, Munich, Germany
– sequence: 21
  givenname: Benedikt
  surname: Wiestler
  fullname: Wiestler, Benedikt
  organization: Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, Munich, Germany
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38703470$$D View this record in MEDLINE/PubMed
BookMark eNqNkktv1DAUhSNURB_0D7BAWbLJ4Fdiu0JIo1JgpEEspqwtx7kZOTjOYCeg-fc4pFSoEgVv_NA5x9ef73l24gcPWfYCoxVGuHrdrbw1bkUQYemAVhg_yc4IwbTApSAnf6xPs8sYO5SGQIhX1bPslAqOKOPoLHu33d0W681Vvs4bgEPuQAdv_T4HH6GvHeTtEHJtzBT0CPmnXVJEO_g8wr4HP-oxbZ5nT1vtIlzezRfZl_c3t9cfi-3nD5vr9bYwJSdjAYQDMFNKYEyLSmPDS8qEaCqcyqK1FJVBRMuGytogSdu6IbI1pWgEq43E9CLbLLnNoDt1CLbX4agGbdWvgyHslQ5jwgKKCCJZ1dRcAGcC1YIRXEouawIUC1OmLLpkTf6gjz-0c_eBGKkZserUjFjNiNWCOLleLa5DGL5NEEfV22jAOe1hmKKiqESSYSJ5kr68k051D819-m_2SSAWgQlDjAFaZezCcwzausfLIA-s_1X7m8UE6Yu-WwgqGgveQGMDmDExtI_b3z6wG2eTSruvcITYDVPw6fMVVpEopHZz_83tR1jqvBLN7736e8C_bv8JiNnj8Q
CitedBy_id crossref_primary_10_1002_hbm_70104
crossref_primary_10_1038_s41598_024_72649_9
crossref_primary_10_1186_s13195_024_01606_5
crossref_primary_10_1002_acn3_52311
crossref_primary_10_1142_S0129065725500066
crossref_primary_10_57197_JDR_2024_0078
Cites_doi 10.1002/hbm.24750
10.3389/fneur.2020.546744
10.3389/fmed.2022.797586
10.1016/S1474-4422(17)30470-2
10.1109/ISBI48211.2021.9433952
10.1109/JBHI.2022.3151741
10.1093/brain/aws246
10.1016/j.msard.2019.01.042
10.1016/j.compmedimag.2020.101828
10.1109/ISBI48211.2021.9434127
10.1016/j.media.2021.102312
10.1101/2022.06.11.495736
10.1016/j.jalz.2016.06.205
10.1038/s41467-022-33407-5
10.1016/S0140-6736(18)30481-1
10.1038/s41592-020-01008-z
10.1038/s41598-023-31207-5
10.1038/s41598-018-31911-7
10.1007/978-3-319-67389-9_44
10.1016/j.neuroimage.2011.11.032
10.1016/j.neuroimage.2020.117471
10.3389/fnins.2020.00125
10.1038/s41598-020-79925-4
10.1016/j.neuroimage.2016.12.064
10.1002/hbm.26424
10.1177/17562864231161892
10.1002/hbm.25695
10.1016/j.neuroimage.2021.118589
10.1016/j.nicl.2020.102357
10.3389/fnins.2022.975862
10.1007/s12021-017-9348-7
10.1016/j.compbiomed.2022.105402
10.1016/j.neuroimage.2018.07.005
10.1007/s00234-022-03019-3
10.1016/j.neuroimage.2006.01.015
ContentType Journal Article
Copyright 2024 The Author(s)
The Author(s)
Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: 2024 The Author(s)
– notice: The Author(s)
– notice: Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.
DBID 6I.
AAFTH
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ADTOC
UNPAY
DOA
DOI 10.1016/j.nicl.2024.103611
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList
MEDLINE
MEDLINE - Academic



Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 4
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2213-1582
EndPage 103611
ExternalDocumentID oai_doaj_org_article_282946db78e7480b84215979b2e318c5
10.1016/j.nicl.2024.103611
38703470
10_1016_j_nicl_2024_103611
S2213158224000500
1_s2_0_S2213158224000500
Genre Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NINDS NIH HHS
  grantid: R01 NS112161
GroupedDBID .1-
.FO
0R~
1P~
457
53G
5VS
AAEDT
AAEDW
AAIKJ
AALRI
AAXUO
AAYWO
ABMAC
ACGFS
ACVFH
ADBBV
ADCNI
ADEZE
ADRAZ
ADVLN
AEUPX
AEXQZ
AFJKZ
AFPUW
AFRHN
AFTJW
AGHFR
AIGII
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
AOIJS
APXCP
BAWUL
BCNDV
DIK
EBS
EJD
FDB
GROUPED_DOAJ
HYE
HZ~
IPNFZ
IXB
KQ8
M41
M48
M~E
O-L
O9-
OK1
RIG
ROL
RPM
SSZ
Z5R
0SF
6I.
AACTN
AAFTH
AFCTW
NCXOZ
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ADTOC
UNPAY
ID FETCH-LOGICAL-c572t-e27ee4c59e44a86a1c753488d617663b986c02a9d39bc093fbd29fc58d84bc913
IEDL.DBID M48
ISSN 2213-1582
IngestDate Fri Oct 03 12:54:10 EDT 2025
Sun Oct 26 04:13:59 EDT 2025
Thu Sep 04 18:03:56 EDT 2025
Sat Sep 06 06:29:51 EDT 2025
Thu Apr 24 23:07:06 EDT 2025
Wed Oct 01 01:54:15 EDT 2025
Sat Nov 09 16:00:55 EST 2024
Tue Feb 25 20:05:20 EST 2025
Tue Aug 26 16:33:11 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords RRMS
N/A
CNN
PPMS
MRI
PV
Lesion Segmentation
CPU
SAMSEG
GPU
SC
Multiple Sclerosis
White Matter Lesions
ASD
PPVL
DSC
WM
PPV
FLAIR
ON
SPMS
MS
Artificial Intelligence
AI
IQR
IT
CIS
LST
LST-LPA
Deep Learning
TE
Magnetic Resonance Imaging
SensL
TI
LST-LGA
JC
ReLU
FA
T1w
TR
positive predictive value
not applicable/available
central processing unit
inversion time
artificial intelligence
average surface distance
echo time
convolutional neural networks
lesion-wise positive predictive value
secondary progressive multiple sclerosis
rectified linear unit
lesion segmentation tool lesion growth algorithm
repetition time
T1-weighted
optic neuritis
subcortical
primary progressive multiple sclerosis
periventricular
flip angle
magnetic resonance imaging
lesion-wise sensitivity
interquartile range
white matter
lesion segmentation tool lesion prediction algorithm
fluid-attenuated inversion recovery
dice similarity coefficient
multiple sclerosis
infratentorial
sequence adaptive multimodal segmentation
relapsing-remitting multiple sclerosis
lesion segmentation tool
juxtacortical
graphics processing unit
clinically isolated syndrome
Language English
License This is an open access article under the CC BY-NC-ND license.
Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.
cc-by-nc-nd
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c572t-e27ee4c59e44a86a1c753488d617663b986c02a9d39bc093fbd29fc58d84bc913
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-2682-3641
0000-0002-9545-2709
OpenAccessLink http://journals.scholarsportal.info/openUrl.xqy?doi=10.1016/j.nicl.2024.103611
PMID 38703470
PQID 3050941297
PQPubID 23479
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_282946db78e7480b84215979b2e318c5
unpaywall_primary_10_1016_j_nicl_2024_103611
proquest_miscellaneous_3050941297
pubmed_primary_38703470
crossref_citationtrail_10_1016_j_nicl_2024_103611
crossref_primary_10_1016_j_nicl_2024_103611
elsevier_sciencedirect_doi_10_1016_j_nicl_2024_103611
elsevier_clinicalkeyesjournals_1_s2_0_S2213158224000500
elsevier_clinicalkey_doi_10_1016_j_nicl_2024_103611
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2024
2024-00-00
20240101
2024-01-01
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 2024
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle NeuroImage clinical
PublicationTitleAlternate Neuroimage Clin
PublicationYear 2024
Publisher Elsevier Inc
Elsevier
Publisher_xml – name: Elsevier Inc
– name: Elsevier
References Lesjak, Galimzianova, Koren, Lukin, Pernus, Likar, Spiclin (b0125) 2018; 16
Rakić, Vercruyssen, Van Eyndhoven, de la Rosa, Jain, Van Huffel, Maes, Smeets, Sima (b0165) 2021; 31
Ronneberger, Fischer, Brox (b0170) 2015
Pongratz, Bussas, Schmidt, Grahl, Gasperi, El Husseini, Harabacz, Pineker, Sepp, Grundl, Wiestler, Kirschke, Zimmer, Berthele, Hemmer, Mühlau (b0160) 2023; 37
La Rosa, Abdulkadir, Fartaria, Rahmanzadeh, Lu, Galbusera, Barakovic, Thiran, Granziera, Cuadra (b0120) 2020; 27
Thompson, Baranzini, Geurts, Hemmer, Ciccarelli (b0200) 2018; 391
(arXiv:1706.05721). arXiv. https://doi.org/10.48550/arXiv.1706.05721.
Billot, B., Cerri, S., Leemput, K. V., Dalca, A. V., & Iglesias, J. E. (2021). Joint Segmentation Of Multiple Sclerosis Lesions And Brain Anatomy In MRI Scans Of Any Contrast And Resolution With CNNs.
Kofler, Berger, Waldmannstetter, Lipkova, Ezhov, Tetteh, Kirschke, Zimmer, Wiestler, Menze (b0110) 2020; 14
Krishnan, Song, Clayton, Jia, de Crespigny, Carano (b0115) 2023; 13
Menze, Isensee, Wiest, Wiestler, Maier-Hein, Reyes, Bakas (b0150) 2021; 88
Li, Jiang, Zhang, Wang, Wang, Zheng, Menze (b0130) 2018; 183
Yushkevich, Piven, Hazlett, Smith, Ho, Gee, Gerig (b0230) 2006; 31
Çiçek, Abdulkadir, Lienkamp, Brox, Ronneberger (b0040) 2016
(4), 373–374.
Vanderbecq, Xu, Stroer, Couvy-Duchesne, Diaz Melo, Dormont, Colliot, Alzheimer’s Disease Neuroimaging, I. (b0215) 2020; 27
Yushkevich, Pluta, Wang, Wisse, Das, Wolk (b0235) 2016; 12
Filippi, Bar-Or, Piehl, Preziosa, Solari, Vukusic, Rocca (b0065) 2018; 4
Thakur, Schindler, Bilello, Bakas (b0190) 2022; 9
(p. 2022.06.11.495736). bioRxiv. https://doi.org/10.1101/2022.06.11.495736.
Wang, L., Lee, C.-Y., Tu, Z., & Lazebnik, S. (2015).
Ashtari, Barile, Van Huffel, Sappey-Marinier (b0010) 2022; 16
Schmidt, Gaser, Arsic, Buck, Förschler, Berthele, Hoshi, Ilg, Schmid, Zimmer, Hemmer, Mühlau (b0180) 2012; 59
World Medical Association. (2001). World Medical Association Declaration of Helsinki. Ethical principles for medical research involving human subjects.
,
Gaser, C., Dahnke, R., Thompson, P. M., Kurth, F., Luders, E., & Initiative, A. D. N. (2022).
Zhang, Oguz (b0250) 2021
Cerri, Puonti, Meier, Wuerfel, Mühlau, Siebner, Van Leemput (b0035) 2021; 225
Commowick, Kain, Casey, Ameli, Ferré, Kerbrat, Tourdias, Cervenansky, Camarasu-Pop, Glatard, Vukusic, Edan, Barillot, Dojat, Cotton (b0050) 2021; 244
655–658. https://doi.org/10.1109/ISBI48211.2021.9433952.
(arXiv:1505.02496). arXiv. https://doi.org/10.48550/arXiv.1505.02496.
Tripoliti, Zelilidou, Vlahos, Konitsiotis, Fotiadis (b0205) 2019
Antonelli, Reinke, Bakas, Farahani, Kopp-Schneider, Landman, Litjens, Menze, Ronneberger, Summers, van Ginneken, Bilello, Bilic, Christ, Do, Gollub, Heckers, Huisman, Jarnagin, Cardoso (b0005) 2022; 13
Gentile, Jenkinson, Griffanti, Luchetti, Leoncini, Inderyas, Mortilla, Cortese, De Stefano, Battaglini (b0075) 2023
Carass, Roy, Jog, Cuzzocreo, Magrath, Gherman, Button, Nguyen, Prados, Sudre, Jorge Cardoso, Cawley, Ciccarelli, Wheeler-Kingshott, Ourselin, Catanese, Deshpande, Maurel, Commowick, Pham (b0030) 2017; 148
McKinley, Wepfer, Aschwanden, Grunder, Muri, Rummel, Verma, Weisstanner, Reyes, Salmen, Chan, Wagner, Wiest (b0145) 2021; 11
Hapfelmeier, On, Mühlau, Kirschke, Berthele, Gasperi, Mansmann, Wuschek, Bussas, Boeker, Bayas, Senel, Havla, Kowarik, Kuhn, Gatz, Spengler, Wiestler, Grundl, Hemmer (b0085) 2023; 16
Hashemi, Akhbari, Jutten (b0090) 2022; 145
Valverde, Salem, Cabezas, Pareto, Vilanova, Ramió-Torrentà, Rovira, Salvi, Oliver, Lladó (b0210) 2019; 21
Thompson, Banwell, Barkhof, Carroll, Coetzee, Comi, Correale, Fazekas, Filippi, Freedman, Fujihara, Galetta, Hartung, Kappos, Lublin, Marrie, Miller, Miller, Montalban, Cohen (b0195) 2018; 17
Calabrese, Poretto, Favaretto, Alessio, Bernardi, Romualdi, Rinaldi, Perini, Gallo (b0025) 2012; 135
Commowick, Istace, Kain, Laurent, Leray, Simon, Pop, Girard, Ameli, Ferre, Kerbrat, Tourdias, Cervenansky, Glatard, Beaumont, Doyle, Forbes, Knight, Khademi, Barillot (b0045) 2018; 8
Ma, Zhang, Cabezas, Song, Tang, Liu, Cai, Barnett, Wang (b0140) 2022; 26
Pati, Baid, Edwards, Sheller, Wang, Reina, Foley, Gruzdev, Karkada, Davatzikos, Sako, Ghodasara, Bilello, Mohan, Vollmuth, Brugnara, Preetha, Sahm, Maier-Hein, Bakas (b0155) 2022; 13
Yushkevich, P. (2023).
Kamraoui, Ta, Tourdias, Mansencal, Manjon, Coup (b0105) 2022; 76
Brune, Høgestøl, Cengija, Berg-Hansen, Sowa, Nygaard, Harbo, Beyer (b0020) 2020; 11
Isensee, Schell, Pflueger, Brugnara, Bonekamp, Neuberger, Wick, Schlemmer, Heiland, Wick, Bendszus, Maier-Hein, Kickingereder (b0095) 2019; 40
Li, Zhao, Jiang, Cheng, Zhu, Wu, Jing, Zhang, Wen, Sachdev, Wang, Liu, Li (b0135) 2022; 43
1971–1974. https://doi.org/10.1109/ISBI48211.2021.9434127.
Diaz-Hurtado, Martínez-Heras, Solana, Casas-Roma, Llufriu, Kanber, Prados (b0060) 2022; 64
[C++]. https://github.com/pyushkevich/greedy (Original work published 2016).
Grahl, Pongratz, Schmidt, Engl, Bussas, Radetz, Gonzalez-Escamilla, Groppa, Zipp, Lukas, Kirschke, Zimmer, Hoshi, Berthele, Hemmer, Mühlau (b0080) 2019; 29
Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017).
Isensee, Jaeger, Kohl, Petersen, Maier-Hein (b0100) 2021; 18
Zeng, Gu, Liu, Zhao (b0245) 2020; 14
Li (10.1016/j.nicl.2024.103611_b0130) 2018; 183
Kofler (10.1016/j.nicl.2024.103611_b0110) 2020; 14
McKinley (10.1016/j.nicl.2024.103611_b0145) 2021; 11
Commowick (10.1016/j.nicl.2024.103611_b0045) 2018; 8
Kamraoui (10.1016/j.nicl.2024.103611_b0105) 2022; 76
Li (10.1016/j.nicl.2024.103611_b0135) 2022; 43
10.1016/j.nicl.2024.103611_b0015
Tripoliti (10.1016/j.nicl.2024.103611_b0205) 2019
10.1016/j.nicl.2024.103611_b0055
Rakić (10.1016/j.nicl.2024.103611_b0165) 2021; 31
Isensee (10.1016/j.nicl.2024.103611_b0095) 2019; 40
10.1016/j.nicl.2024.103611_b0175
Calabrese (10.1016/j.nicl.2024.103611_b0025) 2012; 135
Zeng (10.1016/j.nicl.2024.103611_b0245) 2020; 14
Isensee (10.1016/j.nicl.2024.103611_b0100) 2021; 18
Zhang (10.1016/j.nicl.2024.103611_b0250) 2021
Ronneberger (10.1016/j.nicl.2024.103611_b0170) 2015
Filippi (10.1016/j.nicl.2024.103611_b0065) 2018; 4
Pongratz (10.1016/j.nicl.2024.103611_b0160) 2023; 37
Diaz-Hurtado (10.1016/j.nicl.2024.103611_b0060) 2022; 64
Menze (10.1016/j.nicl.2024.103611_b0150) 2021; 88
Yushkevich (10.1016/j.nicl.2024.103611_b0235) 2016; 12
Hashemi (10.1016/j.nicl.2024.103611_b0090) 2022; 145
Thakur (10.1016/j.nicl.2024.103611_b0190) 2022; 9
Cerri (10.1016/j.nicl.2024.103611_b0035) 2021; 225
10.1016/j.nicl.2024.103611_b0240
Brune (10.1016/j.nicl.2024.103611_b0020) 2020; 11
Thompson (10.1016/j.nicl.2024.103611_b0195) 2018; 17
Thompson (10.1016/j.nicl.2024.103611_b0200) 2018; 391
Schmidt (10.1016/j.nicl.2024.103611_b0180) 2012; 59
Krishnan (10.1016/j.nicl.2024.103611_b0115) 2023; 13
Valverde (10.1016/j.nicl.2024.103611_b0210) 2019; 21
Gentile (10.1016/j.nicl.2024.103611_b0075) 2023
10.1016/j.nicl.2024.103611_b0070
Ashtari (10.1016/j.nicl.2024.103611_b0010) 2022; 16
Pati (10.1016/j.nicl.2024.103611_b0155) 2022; 13
Hapfelmeier (10.1016/j.nicl.2024.103611_b0085) 2023; 16
Carass (10.1016/j.nicl.2024.103611_b0030) 2017; 148
Çiçek (10.1016/j.nicl.2024.103611_b0040) 2016
Ma (10.1016/j.nicl.2024.103611_b0140) 2022; 26
Commowick (10.1016/j.nicl.2024.103611_b0050) 2021; 244
Yushkevich (10.1016/j.nicl.2024.103611_b0230) 2006; 31
10.1016/j.nicl.2024.103611_b0225
Vanderbecq (10.1016/j.nicl.2024.103611_b0215) 2020; 27
10.1016/j.nicl.2024.103611_b0220
Antonelli (10.1016/j.nicl.2024.103611_b0005) 2022; 13
La Rosa (10.1016/j.nicl.2024.103611_b0120) 2020; 27
Lesjak (10.1016/j.nicl.2024.103611_b0125) 2018; 16
Grahl (10.1016/j.nicl.2024.103611_b0080) 2019; 29
38045345 - medRxiv. 2024 Mar 11:2023.11.23.23298966. doi: 10.1101/2023.11.23.23298966.
References_xml – volume: 31
  year: 2021
  ident: b0165
  article-title: icobrain ms 5.1: Combining unsupervised and supervised approaches for improving the detection of multiple sclerosis lesions
  publication-title: NeuroImage: Clinical
– volume: 18
  year: 2021
  ident: b0100
  article-title: nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation
  publication-title: Nat. Methods
– volume: 40
  start-page: 4952
  year: 2019
  end-page: 4964
  ident: b0095
  article-title: Automated brain extraction of multisequence MRI using artificial neural networks
  publication-title: Hum. Brain Mapp.
– volume: 26
  start-page: 2680
  year: 2022
  end-page: 2692
  ident: b0140
  article-title: Multiple sclerosis lesion analysis in brain magnetic resonance images: techniques and clinical applications
  publication-title: IEEE J. Biomed. Health Inform.
– volume: 13
  start-page: 4128
  year: 2022
  ident: b0005
  article-title: The medical segmentation decathlon
  publication-title: NatureCommunications
– volume: 88
  year: 2021
  ident: b0150
  article-title: Analyzing magnetic resonance imaging data from glioma patients using deep learning
  publication-title: Comput. Med. Imaging Graph.
– start-page: 11
  year: 2021
  end-page: 29
  ident: b0250
  article-title: Multiple Sclerosis Lesion Segmentation—A Survey of Supervised CNN-Based Methods
  publication-title: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
– volume: 225
  year: 2021
  ident: b0035
  article-title: A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis
  publication-title: Neuroimage
– reference: (4), 373–374.
– reference: , 655–658. https://doi.org/10.1109/ISBI48211.2021.9433952.
– volume: 17
  start-page: 162
  year: 2018
  end-page: 173
  ident: b0195
  article-title: Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria
  publication-title: The Lancet Neurology
– year: 2023
  ident: b0075
  article-title: BIANCA-MS: An optimized tool for automated multiple sclerosis lesion segmentation
  publication-title: Hum. Brain Mapp.
– volume: 391
  start-page: 1622
  year: 2018
  end-page: 1636
  ident: b0200
  article-title: Multiple sclerosis
  publication-title: Lancet (london, England)
– volume: 37
  year: 2023
  ident: b0160
  article-title: Lesion location across diagnostic regions in multiple sclerosis
  publication-title: NeuroImage: Clinical
– reference: (arXiv:1706.05721). arXiv. https://doi.org/10.48550/arXiv.1706.05721.
– volume: 145
  year: 2022
  ident: b0090
  article-title: Delve into Multiple Sclerosis (MS) lesion exploration: A modified attention U-Net for MS lesion segmentation in Brain MRI
  publication-title: Comput. Biol. Med.
– volume: 16
  start-page: 51
  year: 2018
  end-page: 63
  ident: b0125
  article-title: A novel public MR image dataset of multiple sclerosis patients with lesion segmentations based on multi-rater consensus
  publication-title: Neuroinformatics
– volume: 31
  start-page: 1116
  year: 2006
  end-page: 1128
  ident: b0230
  article-title: User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability
  publication-title: Neuroimage
– volume: 16
  year: 2022
  ident: b0010
  article-title: New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
  publication-title: Front. Neurosci.
– reference: , 1971–1974. https://doi.org/10.1109/ISBI48211.2021.9434127.
– volume: 148
  start-page: 77
  year: 2017
  end-page: 102
  ident: b0030
  article-title: Longitudinal multiple sclerosis lesion segmentation: resource and challenge
  publication-title: Neuroimage
– volume: 27
  year: 2020
  ident: b0215
  article-title: Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients
  publication-title: Neuroimage Clin
– volume: 8
  start-page: 13650
  year: 2018
  ident: b0045
  article-title: Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure
  publication-title: Sci Rep
– volume: 29
  start-page: 124
  year: 2019
  end-page: 129
  ident: b0080
  article-title: Evidence for a white matter lesion size threshold to support the diagnosis of relapsing remitting multiple sclerosis
  publication-title: Mult. Scler. Relat. Disord.
– volume: 244
  year: 2021
  ident: b0050
  article-title: Multiple sclerosis lesions segmentation from multiple experts: The MICCAI 2016 challenge dataset
  publication-title: Neuroimage
– volume: 13
  year: 2023
  ident: b0115
  article-title: Multi-arm U-Net with dense input and skip connectivity for T2 lesion segmentation in clinical trials of multiple sclerosis
  publication-title: Sci. Rep.
– volume: 4
  year: 2018
  ident: b0065
  article-title: Multiple sclerosis
  publication-title: Nat. Rev. Dis. Primers
– volume: 76
  year: 2022
  ident: b0105
  article-title: DeepLesionBrain: towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
  publication-title: Med. Image Anal.
– reference: World Medical Association. (2001). World Medical Association Declaration of Helsinki. Ethical principles for medical research involving human subjects.
– reference: Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017).
– volume: 27
  year: 2020
  ident: b0120
  article-title: Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: A deep learning method based on FLAIR and MP2RAGE
  publication-title: NeuroImage: Clinical
– reference: ,
– reference: Yushkevich, P. (2023).
– reference: [C++]. https://github.com/pyushkevich/greedy (Original work published 2016).
– reference: Gaser, C., Dahnke, R., Thompson, P. M., Kurth, F., Luders, E., & Initiative, A. D. N. (2022).
– volume: 9
  year: 2022
  ident: b0190
  article-title: Clinically deployed computational assessment of multiple sclerosis lesions
  publication-title: Front. Med.
– volume: 21
  year: 2019
  ident: b0210
  article-title: One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks
  publication-title: NeuroImage: Clinical
– reference: Billot, B., Cerri, S., Leemput, K. V., Dalca, A. V., & Iglesias, J. E. (2021). Joint Segmentation Of Multiple Sclerosis Lesions And Brain Anatomy In MRI Scans Of Any Contrast And Resolution With CNNs.
– volume: 11
  year: 2020
  ident: b0020
  article-title: LesionQuant for assessment of MRI in multiple sclerosis—a promising supplement to the visual scan inspection
  publication-title: Front. Neurol.
– start-page: 284
  year: 2019
  end-page: 287
  ident: b0205
  article-title: ProMiSi Architecture—A Tool for the Estimation of the Progression of Multiple Sclerosis Disease using MRI
  publication-title: 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)
– volume: 135
  start-page: 2952
  year: 2012
  end-page: 2961
  ident: b0025
  article-title: Cortical lesion load associates with progression of disability in multiple sclerosis
  publication-title: Brain: A J. Neurol.
– volume: 14
  start-page: 125
  year: 2020
  ident: b0110
  article-title: BraTS toolkit: translating BraTS brain tumor segmentation algorithms into clinical and scientific practice
  publication-title: Front. Neurosci.
– volume: 59
  start-page: 3774
  year: 2012
  end-page: 3783
  ident: b0180
  article-title: An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis
  publication-title: Neuroimage
– volume: 12
  start-page: P126
  year: 2016
  end-page: P127
  ident: b0235
  article-title: Fast Automatic Segmentation of Hippocampal Subfields and Medial Temporal Lobe Subregions In 3 Tesla and 7 Tesla T2-Weighted MRI
  publication-title: Alzheimer’s & Dementia
– volume: 13
  start-page: 7346
  year: 2022
  ident: b0155
  article-title: Federated learning enables big data for rare cancer boundary detection
  publication-title: Nat. Commun.
– volume: 16
  year: 2023
  ident: b0085
  article-title: Retrospective cohort study to devise a treatment decision score predicting adverse 24-month radiological activity in early multiple sclerosis
  publication-title: Ther. Adv. Neurol. Disord.
– volume: 43
  start-page: 929
  year: 2022
  end-page: 939
  ident: b0135
  article-title: White matter hyperintensities segmentation using an ensemble of neural networks
  publication-title: Hum. Brain Mapp.
– start-page: 424
  year: 2016
  end-page: 432
  ident: b0040
  article-title: 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
  publication-title: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016
– reference: (arXiv:1505.02496). arXiv. https://doi.org/10.48550/arXiv.1505.02496.
– volume: 64
  start-page: 2103
  year: 2022
  end-page: 2117
  ident: b0060
  article-title: Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review
  publication-title: Neuroradiology
– reference: (p. 2022.06.11.495736). bioRxiv. https://doi.org/10.1101/2022.06.11.495736.
– volume: 14
  year: 2020
  ident: b0245
  article-title: Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI.
  publication-title: Neuroinformatics
– volume: 183
  start-page: 650
  year: 2018
  end-page: 665
  ident: b0130
  article-title: Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images
  publication-title: Neuroimage
– volume: 11
  start-page: 1087
  year: 2021
  ident: b0145
  article-title: Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks
  publication-title: Sci Rep
– start-page: 234
  year: 2015
  end-page: 241
  ident: b0170
  article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation
  publication-title: Medical Image Computing and Computer-Assisted Intervention –
– reference: Wang, L., Lee, C.-Y., Tu, Z., & Lazebnik, S. (2015).
– ident: 10.1016/j.nicl.2024.103611_b0240
– volume: 40
  start-page: 4952
  issue: 17
  year: 2019
  ident: 10.1016/j.nicl.2024.103611_b0095
  article-title: Automated brain extraction of multisequence MRI using artificial neural networks
  publication-title: Hum. Brain Mapp.
  doi: 10.1002/hbm.24750
– volume: 11
  year: 2020
  ident: 10.1016/j.nicl.2024.103611_b0020
  article-title: LesionQuant for assessment of MRI in multiple sclerosis—a promising supplement to the visual scan inspection
  publication-title: Front. Neurol.
  doi: 10.3389/fneur.2020.546744
– volume: 9
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0190
  article-title: Clinically deployed computational assessment of multiple sclerosis lesions
  publication-title: Front. Med.
  doi: 10.3389/fmed.2022.797586
– volume: 17
  start-page: 162
  issue: 2
  year: 2018
  ident: 10.1016/j.nicl.2024.103611_b0195
  article-title: Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria
  publication-title: The Lancet Neurology
  doi: 10.1016/S1474-4422(17)30470-2
– ident: 10.1016/j.nicl.2024.103611_b0055
  doi: 10.1109/ISBI48211.2021.9433952
– volume: 26
  start-page: 2680
  issue: 6
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0140
  article-title: Multiple sclerosis lesion analysis in brain magnetic resonance images: techniques and clinical applications
  publication-title: IEEE J. Biomed. Health Inform.
  doi: 10.1109/JBHI.2022.3151741
– start-page: 284
  year: 2019
  ident: 10.1016/j.nicl.2024.103611_b0205
  article-title: ProMiSi Architecture—A Tool for the Estimation of the Progression of Multiple Sclerosis Disease using MRI
– start-page: 11
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0250
  article-title: Multiple Sclerosis Lesion Segmentation—A Survey of Supervised CNN-Based Methods
– volume: 135
  start-page: 2952
  issue: Pt 10
  year: 2012
  ident: 10.1016/j.nicl.2024.103611_b0025
  article-title: Cortical lesion load associates with progression of disability in multiple sclerosis
  publication-title: Brain: A J. Neurol.
  doi: 10.1093/brain/aws246
– start-page: 234
  year: 2015
  ident: 10.1016/j.nicl.2024.103611_b0170
  article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation
– volume: 29
  start-page: 124
  year: 2019
  ident: 10.1016/j.nicl.2024.103611_b0080
  article-title: Evidence for a white matter lesion size threshold to support the diagnosis of relapsing remitting multiple sclerosis
  publication-title: Mult. Scler. Relat. Disord.
  doi: 10.1016/j.msard.2019.01.042
– volume: 88
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0150
  article-title: Analyzing magnetic resonance imaging data from glioma patients using deep learning
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2020.101828
– volume: 21
  year: 2019
  ident: 10.1016/j.nicl.2024.103611_b0210
  article-title: One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks
  publication-title: NeuroImage: Clinical
– volume: 13
  start-page: 4128
  issue: 1
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0005
  article-title: The medical segmentation decathlon
  publication-title: NatureCommunications
– start-page: 424
  year: 2016
  ident: 10.1016/j.nicl.2024.103611_b0040
  article-title: 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
– ident: 10.1016/j.nicl.2024.103611_b0015
  doi: 10.1109/ISBI48211.2021.9434127
– volume: 76
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0105
  article-title: DeepLesionBrain: towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2021.102312
– volume: 37
  year: 2023
  ident: 10.1016/j.nicl.2024.103611_b0160
  article-title: Lesion location across diagnostic regions in multiple sclerosis
  publication-title: NeuroImage: Clinical
– ident: 10.1016/j.nicl.2024.103611_b0070
  doi: 10.1101/2022.06.11.495736
– volume: 12
  start-page: P126
  issue: 7S_Part_2
  year: 2016
  ident: 10.1016/j.nicl.2024.103611_b0235
  article-title: Fast Automatic Segmentation of Hippocampal Subfields and Medial Temporal Lobe Subregions In 3 Tesla and 7 Tesla T2-Weighted MRI
  publication-title: Alzheimer’s & Dementia
  doi: 10.1016/j.jalz.2016.06.205
– volume: 13
  start-page: 7346
  issue: 1
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0155
  article-title: Federated learning enables big data for rare cancer boundary detection
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-022-33407-5
– volume: 391
  start-page: 1622
  issue: 10130
  year: 2018
  ident: 10.1016/j.nicl.2024.103611_b0200
  article-title: Multiple sclerosis
  publication-title: Lancet (london, England)
  doi: 10.1016/S0140-6736(18)30481-1
– volume: 18
  issue: 2
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0100
  article-title: nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation
  publication-title: Nat. Methods
  doi: 10.1038/s41592-020-01008-z
– volume: 13
  issue: 1
  year: 2023
  ident: 10.1016/j.nicl.2024.103611_b0115
  article-title: Multi-arm U-Net with dense input and skip connectivity for T2 lesion segmentation in clinical trials of multiple sclerosis
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-023-31207-5
– volume: 8
  start-page: 13650
  issue: 1
  year: 2018
  ident: 10.1016/j.nicl.2024.103611_b0045
  article-title: Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure
  publication-title: Sci Rep
  doi: 10.1038/s41598-018-31911-7
– ident: 10.1016/j.nicl.2024.103611_b0175
  doi: 10.1007/978-3-319-67389-9_44
– ident: 10.1016/j.nicl.2024.103611_b0225
– volume: 59
  start-page: 3774
  issue: 4
  year: 2012
  ident: 10.1016/j.nicl.2024.103611_b0180
  article-title: An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2011.11.032
– volume: 27
  year: 2020
  ident: 10.1016/j.nicl.2024.103611_b0120
  article-title: Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: A deep learning method based on FLAIR and MP2RAGE
  publication-title: NeuroImage: Clinical
– volume: 225
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0035
  article-title: A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2020.117471
– volume: 14
  start-page: 125
  year: 2020
  ident: 10.1016/j.nicl.2024.103611_b0110
  article-title: BraTS toolkit: translating BraTS brain tumor segmentation algorithms into clinical and scientific practice
  publication-title: Front. Neurosci.
  doi: 10.3389/fnins.2020.00125
– volume: 11
  start-page: 1087
  issue: 1
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0145
  article-title: Simultaneous lesion and brain segmentation in multiple sclerosis using deep neural networks
  publication-title: Sci Rep
  doi: 10.1038/s41598-020-79925-4
– volume: 4
  issue: 1
  year: 2018
  ident: 10.1016/j.nicl.2024.103611_b0065
  article-title: Multiple sclerosis
  publication-title: Nat. Rev. Dis. Primers
– volume: 148
  start-page: 77
  year: 2017
  ident: 10.1016/j.nicl.2024.103611_b0030
  article-title: Longitudinal multiple sclerosis lesion segmentation: resource and challenge
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2016.12.064
– year: 2023
  ident: 10.1016/j.nicl.2024.103611_b0075
  article-title: BIANCA-MS: An optimized tool for automated multiple sclerosis lesion segmentation
  publication-title: Hum. Brain Mapp.
  doi: 10.1002/hbm.26424
– volume: 16
  year: 2023
  ident: 10.1016/j.nicl.2024.103611_b0085
  article-title: Retrospective cohort study to devise a treatment decision score predicting adverse 24-month radiological activity in early multiple sclerosis
  publication-title: Ther. Adv. Neurol. Disord.
  doi: 10.1177/17562864231161892
– volume: 43
  start-page: 929
  issue: 3
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0135
  article-title: White matter hyperintensities segmentation using an ensemble of neural networks
  publication-title: Hum. Brain Mapp.
  doi: 10.1002/hbm.25695
– volume: 244
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0050
  article-title: Multiple sclerosis lesions segmentation from multiple experts: The MICCAI 2016 challenge dataset
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2021.118589
– volume: 31
  year: 2021
  ident: 10.1016/j.nicl.2024.103611_b0165
  article-title: icobrain ms 5.1: Combining unsupervised and supervised approaches for improving the detection of multiple sclerosis lesions
  publication-title: NeuroImage: Clinical
– volume: 14
  year: 2020
  ident: 10.1016/j.nicl.2024.103611_b0245
  article-title: Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI. Frontiers
  publication-title: Neuroinformatics
– volume: 27
  year: 2020
  ident: 10.1016/j.nicl.2024.103611_b0215
  article-title: Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients
  publication-title: Neuroimage Clin
  doi: 10.1016/j.nicl.2020.102357
– volume: 16
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0010
  article-title: New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
  publication-title: Front. Neurosci.
  doi: 10.3389/fnins.2022.975862
– volume: 16
  start-page: 51
  issue: 1
  year: 2018
  ident: 10.1016/j.nicl.2024.103611_b0125
  article-title: A novel public MR image dataset of multiple sclerosis patients with lesion segmentations based on multi-rater consensus
  publication-title: Neuroinformatics
  doi: 10.1007/s12021-017-9348-7
– ident: 10.1016/j.nicl.2024.103611_b0220
– volume: 145
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0090
  article-title: Delve into Multiple Sclerosis (MS) lesion exploration: A modified attention U-Net for MS lesion segmentation in Brain MRI
  publication-title: Comput. Biol. Med.
  doi: 10.1016/j.compbiomed.2022.105402
– volume: 183
  start-page: 650
  year: 2018
  ident: 10.1016/j.nicl.2024.103611_b0130
  article-title: Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2018.07.005
– volume: 64
  start-page: 2103
  issue: 11
  year: 2022
  ident: 10.1016/j.nicl.2024.103611_b0060
  article-title: Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review
  publication-title: Neuroradiology
  doi: 10.1007/s00234-022-03019-3
– volume: 31
  start-page: 1116
  issue: 3
  year: 2006
  ident: 10.1016/j.nicl.2024.103611_b0230
  article-title: User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2006.01.015
– reference: 38045345 - medRxiv. 2024 Mar 11:2023.11.23.23298966. doi: 10.1101/2023.11.23.23298966.
SSID ssj0000800766
Score 2.4467902
Snippet •Free and open-source lesion-segmentation tool (LST-AI), allowing widespread use and community contributions.•Tested on multiple external datasets and...
Highlights•Free and open-source lesion-segmentation tool (LST-AI), allowing widespread use and community contributions. •Tested on multiple external datasets...
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade...
SourceID doaj
unpaywall
proquest
pubmed
crossref
elsevier
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 103611
SubjectTerms Adult
Artificial Intelligence
Brain - diagnostic imaging
Brain - pathology
Deep Learning
Female
Humans
Image Processing, Computer-Assisted - methods
Lesion Segmentation
Magnetic Resonance Imaging
Magnetic Resonance Imaging - methods
Male
Multiple Sclerosis
Multiple Sclerosis - diagnostic imaging
Multiple Sclerosis - pathology
Neuroimaging - methods
Neuroimaging - standards
Radiology
White Matter - diagnostic imaging
White Matter - pathology
White Matter Lesions
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQDzwOiDfhJSNxgwi_4ge35VEVxHLZVurNiu1JRbVNV2RXiH-PvXairUAtB66R7YnGM54Ze-YbhF4Zp4n0ztec-VALDzqeg5LWxotWSalJcOlqYP5NHhyJL8fN8U6rr5QTluGBM-Peppc-IYNTGpTQxGkRjZRRxrF0e-e36KVEm51g6rT4QZFUqZLJCV0JaTYGhEykQnNJ6QVLtAXsv2CQ_nQ4b6Ebm37V_vrZLpc7Rmj_DrpdvEc8y399F12D_h66Pi_v4_fRx6-Lw3r2-R2e4QCwwqUnxAmOwSqcuSXg6KPi1vtNQojA80Ucka7L8AAnZ6UKqX-AjvY_HX44qEufhNo3iq1rYApA-MaAEK2WLfUxBomKGWRCf-TOaOkJa03gxnlieOcCM51vdNDCeUP5Q7TXn_fwGGEBlCowxGvTCW_AdTw0XdyDDjoPRFSIjjyzvoCIp14WSztmi53axGeb-Gwznyv0epqzyhAal45-n7ZiGpngr7cfolDYIhT2KqGoEB830o4VpvFMjAt9v5S0-tssGIpaD5bagVliF4xRTpucgEsaQirUTDOL55I9kispvhylzEa1Tm81bQ_nm8HyhMsjojOmKvQoi9_EEh7PWC5UpPpmksd_4OyT_8HZp-hmWjJfQj1De-sfG3ge3bK1e7HVwN_PLC25
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: Elsevier Free Content
  dbid: IXB
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbtswTCh62OMw7D3vBQ_YbTNiPazHbmm3oh2WXdICuQmWTAcpUieoEwz7-4mxbCzo0A07WiAtgSIpkhJJQt4bp3Ppnc8481UmPOigByXNjBelklLnlcPQwOS7PL0QX2fF7IAc97kw-Kwy6v5Op--0dRwZRWqO1ovFaMoY5bToXkHmRY5-Oxca2zeczY6GOAtaRGp3ZYnwGSLE3JnumRfWnw1uIhOYfi4p3TufdmX8946pm2bofXJ326zLnz_K5fK3o-nkIXkQbcp03C37ETmA5jG5M4m35k_I52_T82x89ikdpxXAOo2dIuZpcGHhyi0hDZZrWnq_xboR6WQaIDCIlrYwv4q5Sc1TcnHy5fz4NIvdEzJfKLbJgCkA4QsDQpRaltQHzySIayWxJiR3Rkufs9JU3DifG167ipnaF7rSwnlD-TNy2KwaeEFSAZQqMLnXphbegKt5VdTBWauh9pCLhNCeZtbH0uLY4WJp-zdklxbpbJHOtqNzQj4MOOuusMat0Ee4FQMkFsXeDayu5zZyhcVLYSErpzSowAhOi2DPGGUcw0CvLxLC-420fd5p0JThR4tbp1Z_woI2CntrqW2Zze0NhkxIMWDu8fRfZ3zXc5kNwo43OGUDq21rOVbrEcFEUwl53rHfQBIeNC8XKsz6ceDHf6Dsy_9c5CtyD7-6aNRrcri53sKbYJ9t3NudAP4C_MMxOw
  priority: 102
  providerName: Elsevier
– databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELbQVgJx4P0IAhQkbpDK8Ss2t-VRFcRWSNuVysmKnUlV2KYrshGCX49n40QsVKVcV55YOx6Pv_F4viHkuXGaKu98xpmvMuFBBz-o8sx4URZKaVo5vBqYHaj9hfhwJI8iTQ7Wwmzl7zfvsJAgNsRxTGB9uMIy3h0lA-6ekJ3FwafpZ-wex3Ke5VKzWBVzvuDWybMh6N86gP4GmNfJta5ZlT--l8vlb4fO3s2-e1G74SrEtyZfd7u12_U__2ByvNz_uUVuROyZTntjuU2uQHOHXJ3F7Ppd8vbj_DCbvn-VTtMKYJXGjhLHaQh14dQtIQ0INy2975BfIp3Nwwi8bEtbOD6NNUzNPbLYe3f4Zj-LXRYyLwu2zoAVAMJLA0KUWpW5DxFM2NaVQu5I7oxWnrLSVNw4Tw2vXcVM7aWutHDe5Pw-mTRnDTwkqYA8L8BQr00tvAFX80rWIairofZARULyYQWsjxTk2AljaYe3Zl8sqseiemyvnoS8GGVWPQHHhaNf48KOI5E8e_NDWAMb96LF5LFQlSs0FEJTp0XAPaYwjuGFsJcJ4YNZ2KE-NXjU8KGTC6cuzpOCNjqF1ua2ZZbaOZorWis-36WS0oTIUTLinh7P_HPGZ4PN2uAUMNNTNnDWtZYjq48IUK5IyIPemEeV8OChuSjCrC9H676EZh_93_DHZLL-1sGTgNjW7mncqr8AsM83ow
  priority: 102
  providerName: Unpaywall
Title LST-AI: A deep learning ensemble for accurate MS lesion segmentation
URI https://www.clinicalkey.com/#!/content/1-s2.0-S2213158224000500
https://www.clinicalkey.es/playcontent/1-s2.0-S2213158224000500
https://dx.doi.org/10.1016/j.nicl.2024.103611
https://www.ncbi.nlm.nih.gov/pubmed/38703470
https://www.proquest.com/docview/3050941297
https://doi.org/10.1016/j.nicl.2024.103611
https://doaj.org/article/282946db78e7480b84215979b2e318c5
UnpaywallVersion publishedVersion
Volume 42
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: KQ8
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: Directory of Open Access Journals
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: DOA
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVESC
  databaseName: Elsevier Free Content
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: IXB
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVBFR
  databaseName: Free Medical Journals - Free Access to All
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: DIK
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: http://www.freemedicaljournals.com
  providerName: Flying Publisher
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: M~E
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: AKRWK
  dateStart: 20120101
  isFulltext: true
  providerName: Library Specific Holdings
– providerCode: PRVAQN
  databaseName: PubMed
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: RPM
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/
  providerName: National Library of Medicine
– providerCode: PRVFZP
  databaseName: Scholars Portal Journals: Open Access
  customDbUrl:
  eissn: 2213-1582
  dateEnd: 20250131
  omitProxy: true
  ssIdentifier: ssj0000800766
  issn: 2213-1582
  databaseCode: M48
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: http://journals.scholarsportal.info
  providerName: Scholars Portal
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3db9MwELemTeLjAfE5wkdlJN4gyLGd2EZCqAOmDdEJqatUnqzYuVRMWVqaVrD_HrtxAhPV4IGXPES-ODrf-X539t0h9FwZSTJrbMyoLWJuQbp9MEtiZXkuskySwvjQwOgkO5rwj9N0uoO6dkeBgc1W1873k5osq1c_vl28dQr_5tddLV9E1vl6lPsc8syn-u45S6V8K4dRgPtnAR25Hwi5M9tJL9mnTRn_S2bqTxh6E11f14v84nteVb-ZpsPb6FbAlHjYCsEdtAP1XXRtFE7N76H3n8an8fD4NR7iAmCBQ6eIGXYuLJybCrBDrji3du3rRuDR2I3wQTTcwOw85CbV99Hk8MPpu6M4dE-IbSroKgYqALhNFXCeyyxPrPNMnLoWma8JyYySmSU0VwVTxhLFSlNQVdpUFpIbqxL2AO3W8xoeIswhSQQoYqUquVVgSlakpXPWSigtEB6hpOOZtqG0uO9wUenuDtmZ9nzWns-65XOEXvQ0i7awxpWjD_xS9CN9UezNi_lypoOOaX8ozLPCCAmCS2Ikd3hGCWWoD_TaNEKsW0jd5Z26ndJ96OuVU4ttVNB0sqoT3VBN9JjShCVpey2XpIREKO0pA55pccpfZ3zWSZl2yu5PcPIa5utGM1-thzuIJiK034pfzxLmdl7GhZv1ZS-P_8DZR_-Ds4_RDf_JNjT1BO2ulmt46sDaygw2QQ73PJ4eDDbaOEB7k5PPwy8_AeewOpQ
linkProvider Scholars Portal
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1db9Mw0JqGxOAB8TnCZ5B4g6hx7MQ2b91g6qDdSzupb1bsXKqiLq2WVoh_jy9xIqqhgXh1fLF1vjvftwl5r4yMM2tsxBJbRNyCdHIwo5GyPBdZJuPCoGtgcpGNLvnXeTo_IKddLQymVXrZ38r0Rlr7kYHH5mCzXA6mSUIZTdssyDiNnd1-h6dOO8EqvvlJ72hBlUg0MUsEiBDCF8-0eV7YgNbZiQnH-vOM0r0Lqunjv3dP3dRD75OjXbXJf_7IV6vf7qazh-SBVyrDYbvvR-QAqsfk7sSHzZ-Qz-PpLBqefwqHYQGwCf1TEYvQ2bBwZVYQOtU1zK3dYeOIcDJ1M9CLFtawuPLFSdVTcnn2ZXY6ivzzCZFNRbKNIBEA3KYKOM9lllPrTBPHr0WGTSGZUTKzcZKrgiljY8VKUySqtKksJDdWUfaMHFbrCp6TkAOlAlRspSq5VWBKVqSls9ZKKC3EPCC0w5m2vrc4PnGx0l0S2XeNeNaIZ93iOSAfephN21nj1tkneBT9TOyK3Qysrxfak4XGqDDPCiMkCC5jI7lTaJRQJkFPr00DwrqD1F3hqROV7kfLW5cWf4KC2nN7ramuEx3rGxQZkLSH3CPqv674rqMy7bgdQzh5BetdrRm26-FORxMBOW7Jr0cJc6KXceFW_djT4z9g9sV_bvItORrNJmM9Pr_49pLcwy-ta-oVOdxe7-C1U9a25k3DjL8AZyw0YQ
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELbQVgJx4P0IAhQkbpDK8Ss2t-VRFcRWSNuVysmKnUlV2KYrshGCX49n40QsVKVcV55YOx6Pv_F4viHkuXGaKu98xpmvMuFBBz-o8sx4URZKaVo5vBqYHaj9hfhwJI8iTQ7Wwmzl7zfvsJAgNsRxTGB9uMIy3h0lA-6ekJ3FwafpZ-wex3Ke5VKzWBVzvuDWybMh6N86gP4GmNfJta5ZlT--l8vlb4fO3s2-e1G74SrEtyZfd7u12_U__2ByvNz_uUVuROyZTntjuU2uQHOHXJ3F7Ppd8vbj_DCbvn-VTtMKYJXGjhLHaQh14dQtIQ0INy2975BfIp3Nwwi8bEtbOD6NNUzNPbLYe3f4Zj-LXRYyLwu2zoAVAMJLA0KUWpW5DxFM2NaVQu5I7oxWnrLSVNw4Tw2vXcVM7aWutHDe5Pw-mTRnDTwkqYA8L8BQr00tvAFX80rWIairofZARULyYQWsjxTk2AljaYe3Zl8sqseiemyvnoS8GGVWPQHHhaNf48KOI5E8e_NDWAMb96LF5LFQlSs0FEJTp0XAPaYwjuGFsJcJ4YNZ2KE-NXjU8KGTC6cuzpOCNjqF1ua2ZZbaOZorWis-36WS0oTIUTLinh7P_HPGZ4PN2uAUMNNTNnDWtZYjq48IUK5IyIPemEeV8OChuSjCrC9H676EZh_93_DHZLL-1sGTgNjW7mncqr8AsM83ow
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=LST-AI%3A+A+deep+learning+ensemble+for+accurate+MS+lesion+segmentation&rft.jtitle=NeuroImage+clinical&rft.au=Wiltgen%2C+Tun&rft.au=McGinnis%2C+Julian&rft.au=Schlaeger%2C+Sarah&rft.au=Kofler%2C+Florian&rft.date=2024&rft.eissn=2213-1582&rft.volume=42&rft.spage=103611&rft_id=info:doi/10.1016%2Fj.nicl.2024.103611&rft_id=info%3Apmid%2F38703470&rft.externalDocID=38703470
thumbnail_m http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F22131582%2FS2213158224X00029%2Fcov150h.gif